© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38555
    Prev
    Next
    INDEX
    Explanations

    light colors and shades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłå£°
    -0.09
    ศา
    -0.09
    产ä¸ļåıijå±ķ
    -0.08
     hur
    -0.08
    é«ĺéĢŁå¢ŀéķ¿
    -0.08
    èĪ
    -0.08
    anh
    -0.07
    eel
    -0.07
    toa
    -0.07
    .rgb
    -0.07
    POSITIVE LOGITS
    æħĪ
    0.11
    èĮ¸
    0.09
    髦
    0.09
    椰
    0.09
    çļĦèµĦéĩij
    0.09
    å´ĩ
    0.09
    ä¸Ģ个éĹ®é¢ĺ
    0.09
     Ñģка
    0.09
    纪
    0.09
    èĭı
    0.08
    Activations Density 0.003%

    No Known Activations